remove redundant utils file

archivebox/index/html.py

@@ -5,8 +5,13 @@ from datetime import datetime
 from typing import List, Optional, Iterator, Mapping
 from pathlib import Path
 
+from django.utils.html import format_html
+from collections import defaultdict
+
+from pathlib import Path
+
 from .schema import Link
-from ..system import atomic_write, copy_and_overwrite
+from ..system import atomic_write
 from ..logging_util import printable_filesize
 from ..util import (
     enforce_types,
@@ -23,9 +28,6 @@ from ..config import (
     FOOTER_INFO,
     ARCHIVE_DIR_NAME,
     HTML_INDEX_FILENAME,
-    STATIC_DIR_NAME,
-    ROBOTS_TXT_FILENAME,
-    FAVICON_FILENAME,
 )
 
 MAIN_INDEX_TEMPLATE = str(Path(TEMPLATES_DIR) / 'main_index.html')
@@ -143,3 +145,56 @@ def render_legacy_template(template_path: str, context: Mapping[str, str]) -> st
     with open(template_path, 'r', encoding='utf-8') as template:
         template_str = template.read()
     return Template(template_str).substitute(**context)
+
+
+
+
+def snapshot_icons(snapshot) -> str:
+    from core.models import Snapshot, EXTRACTORS
+
+    archive_results = snapshot.archiveresult_set.filter(status="succeeded")
+    link = snapshot.as_link()
+    path = link.archive_path
+    canon = link.canonical_outputs()
+    output = ""
+    output_template = '<a href="/{}/{}" class="exists-{}" title="{}">{} </a>'
+    icons = {
+        "singlefile": "❶",
+        "wget": "🆆",
+        "dom": "🅷",
+        "pdf": "📄",
+        "screenshot": "💻",
+        "media": "📼",
+        "git": "🅶",
+        "archive_org": "🏛",
+        "readability": "🆁",
+        "mercury": "🅼",
+        "warc": "📦"
+    }
+    exclude = ["favicon", "title", "headers", "archive_org"]
+    # Missing specific entry for WARC
+
+    extractor_items = defaultdict(lambda: None)
+    for extractor, _ in EXTRACTORS:
+        for result in archive_results:
+            if result.extractor == extractor:
+                extractor_items[extractor] = result
+
+    for extractor, _ in EXTRACTORS:
+        if extractor not in exclude:
+            exists = extractor_items[extractor] is not None
+            output += output_template.format(path, canon[f"{extractor}_path"], str(exists),
+                                             extractor, icons.get(extractor, "?"))
+        if extractor == "wget":
+            # warc isn't technically it's own extractor, so we have to add it after wget
+            exists = list((Path(path) / canon["warc_path"]).glob("*.warc.gz"))
+            output += output_template.format(exists[0] if exists else '#', canon["warc_path"], str(bool(exists)), "warc", icons.get("warc", "?"))
+
+        if extractor == "archive_org":
+            # The check for archive_org is different, so it has to be handled separately
+            target_path = Path(path) / "archive.org.txt"
+            exists = target_path.exists()
+            output += '<a href="{}" class="exists-{}" title="{}">{}</a> '.format(canon["archive_org_path"], str(exists),
+                                                                                        "archive_org", icons.get("archive_org", "?"))
+
+    return format_html(f'<span class="files-icons" style="font-size: 1.1em; opacity: 0.8">{output}<span>')